skills/apple-mail/mail-work/SKILL.md
Show work emails only, filtered to Exchange/EWS accounts and corporate email domains. Digest with priorities. Use when user asks about work email, work inbox, or wants to separate work from personal mail. Arguments: optional date range or "today", "yesterday", "this week".
npx skillsauth add aashari/ai-agent-skills mail-workInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Period: $ARGUMENTS (default: today)
Work accounts are EWS/Exchange (detected by ews:// prefix in mailbox URL), plus any IMAP account with a corporate domain (not gmail.com, icloud.com, yahoo.com, hotmail.com, outlook.com).
DB="$HOME/Library/Mail/V10/MailData/Envelope Index"
# EWS/Exchange accounts (most reliable work indicator)
EWS_UUIDS=$(sqlite3 "$DB" "
SELECT DISTINCT substr(url, instr(url,'://')+3, instr(substr(url,instr(url,'://')+3),'/')-1)
FROM mailboxes WHERE url LIKE 'ews://%';" 2>/dev/null)
# All mailbox URLs for work accounts
sqlite3 "$DB" "SELECT DISTINCT url FROM mailboxes WHERE url LIKE 'ews://%';" 2>/dev/null
# Parse $ARGUMENTS
# today: date('now')
# yesterday: date('now','-1 day') to date('now')
# this week: date('now', 'weekday 1', '-7 days') or similar
# default: today
DATE_FILTER="datetime(m.date_received,'unixepoch','localtime') >= '$(date +%Y-%m-%d) 00:00:00'"
sqlite3 "$DB" "
SELECT datetime(m.date_received,'unixepoch','localtime') as dt,
s.subject, a.address as sender, a.comment as name,
mb.url as mailbox, m.ROWID, m.read, m.flagged, m.is_urgent
FROM messages m
JOIN subjects s ON m.subject = s.ROWID
JOIN addresses a ON m.sender = a.ROWID
JOIN mailboxes mb ON m.mailbox = mb.ROWID
WHERE ${DATE_FILTER}
AND m.deleted = 0
AND mb.url LIKE 'ews://%'
AND mb.url NOT LIKE '%Spam%'
AND mb.url NOT LIKE '%Trash%'
AND mb.url NOT LIKE '%Junk%'
AND mb.url NOT LIKE '%Draft%'
ORDER BY m.is_urgent DESC, m.read ASC, m.date_received DESC;" 2>/dev/null
For emails that look substantive, prioritize by automated_conversation:
automated_conversation = 0 = likely real person → read firstautomated_conversation = 1 = transactional (Jira, Slack) → skimautomated_conversation = 2 = bulk automated → count only unless urgentpython3 ~/.claude/skills/_mail-shared/parser.py <ROWID1> <ROWID2>
Group by category. Highlight unread. Surface anything urgent or needing a response. Include a "still needs reply" flag for emails older than 24h that are unread.
testing
Intelligent inbox triage — surface the most important emails across all accounts, prioritized by urgency and requiring attention. Use when user wants a smart overview of what needs their attention, asks "what's important in my email", or wants help deciding what to read first. Arguments: optional time window (default: last 48 hours) or account filter.
data-ai
Find flight bookings, hotel reservations, travel itineraries, and booking confirmations from email. Use when user asks about upcoming trips, travel plans, booking references, flight details, or hotel reservations. Arguments: optional destination, airline, date range, or booking service.
testing
Show who sends the most email, communication frequency analysis, and relationship mapping. Use when user asks who emails them most, top contacts, communication patterns, or wants to understand their email social graph. Arguments: optional time range (default: last 90 days), account filter, or "humans only" to exclude automated senders.
testing
Read and summarize a complete email thread or conversation. Show all messages in order, who said what, and what was decided. Use when user wants to read a specific email thread, catch up on a conversation, or understand what happened in an email chain. Arguments: subject line keywords, ROWID of any message in the thread, sender name, or conversation topic.